decider-4b / eval_results.json
Mapika's picture
decider-4b v2.1
eb5fbdf verified
Raw History Blame Contribute Delete
29.2 kB
{
"model": "decider-4b-v2.1",
"temperature": 1.099,
"temperature_by_type": {
"choice": 1.11,
"noul": 1.56,
"score": 1.287
},
"temperature_fit": {
"global": "one scalar, pooled row NLL on the in-task half of the public regression set without banking77, clinc_oos, mmlu, arc, winogrande and hellaswag (61 tasks, 102,804 rows)",
"by_type": "decider.calibrate.fit_by_type (decider-ai 1.4.0), min_rows 50, on the same regression rows plus our own validation rows (val_jb, val_teacher, val_teacher2, cal_human without mmlu, arc and banking77, val_replay without six excluded families)",
"rows": {
"choice": 108927,
"noul": 1677,
"score": 535
},
"note": "no JevBench or Decision Index item was used for training, selection or temperature"
},
"protocol": "Regression set: eval half of the mixture, 95 tasks (67 in-task / 28 held-out), plain state-first layout, large label sets sub-sampled to 10 options, ECE 15 bins, per-task mean. Own sets (heldout_jb, test_teacher2, cal_human, guard): stored T=1 logits read at the served temperatures, ECE 10 bins top label. Card lanes (fixtures, games, browser, probes, Bespoke, issue #9) through decider-ai 1.4.0 with the map; parents through 1.3.0 at their released temperatures, same rows and seeds; intervals are 95% paired bootstrap. JevBench public items read in process through 1.4.0 with the map; parents' files read earlier through 1.2.1.",
"regression": {
"map": {
"reg_in": 0.8308,
"reg_out": 0.7838,
"reg_in_nll": 0.4145,
"reg_out_nll": 0.5689,
"reg_in_ece": 0.0309,
"reg_out_ece": 0.0775
},
"global_T": {
"reg_in": 0.8308,
"reg_out": 0.7838,
"reg_in_nll": 0.4145,
"reg_out_nll": 0.5703,
"reg_in_ece": 0.0308,
"reg_out_ece": 0.0781
}
},
"own_sets": {
"map": {
"heldout_jb": {
"all": {
"n": 5000,
"accuracy": 0.556,
"nll": 1.2571,
"ece": 0.1466,
"mean_conf": 0.7026
},
"by_type": {
"choice": {
"n": 3293,
"accuracy": 0.5056,
"nll": 1.4995,
"ece": 0.1701,
"mean_conf": 0.6757
},
"noul": {
"n": 1289,
"accuracy": 0.7114,
"nll": 0.6074,
"ece": 0.1013,
"mean_conf": 0.8127
},
"score": {
"n": 418,
"accuracy": 0.4737,
"nll": 1.3504,
"ece": 0.1081,
"mean_conf": 0.5747
}
}
},
"test_teacher2": {
"all": {
"n": 449,
"accuracy": 0.8196,
"nll": 0.4304,
"ece": 0.043,
"mean_conf": 0.8559
},
"by_type": {
"choice": {
"n": 257,
"accuracy": 0.8016,
"nll": 0.5041,
"ece": 0.0569,
"mean_conf": 0.8585
},
"noul": {
"n": 130,
"accuracy": 0.8692,
"nll": 0.2489,
"ece": 0.0479,
"mean_conf": 0.905
},
"score": {
"n": 62,
"accuracy": 0.7903,
"nll": 0.5051,
"ece": 0.0863,
"mean_conf": 0.7423
}
}
},
"guard": {
"all": {
"n": 2994,
"accuracy": 0.8186,
"nll": 0.4866,
"ece": 0.0168,
"mean_conf": 0.8344
},
"by_type": {
"choice": {
"n": 2994,
"accuracy": 0.8186,
"nll": 0.4866,
"ece": 0.0168,
"mean_conf": 0.8344
},
"noul": null,
"score": null
}
},
"val_jb": {
"all": {
"n": 5000,
"accuracy": 0.796,
"nll": 0.5264,
"ece": 0.0157,
"mean_conf": 0.8117
},
"by_type": {
"choice": {
"n": 3374,
"accuracy": 0.7647,
"nll": 0.6258,
"ece": 0.0289,
"mean_conf": 0.7935
},
"noul": {
"n": 1273,
"accuracy": 0.901,
"nll": 0.2233,
"ece": 0.0161,
"mean_conf": 0.8849
},
"score": {
"n": 353,
"accuracy": 0.7167,
"nll": 0.6681,
"ece": 0.0317,
"mean_conf": 0.722
}
}
},
"val_teacher": {
"all": {
"n": 944,
"accuracy": 0.8379,
"nll": 0.4169,
"ece": 0.0369,
"mean_conf": 0.8619
},
"by_type": {
"choice": {
"n": 540,
"accuracy": 0.8315,
"nll": 0.4643,
"ece": 0.0464,
"mean_conf": 0.8547
},
"noul": {
"n": 284,
"accuracy": 0.8873,
"nll": 0.2931,
"ece": 0.0453,
"mean_conf": 0.9088
},
"score": {
"n": 120,
"accuracy": 0.75,
"nll": 0.4969,
"ece": 0.0576,
"mean_conf": 0.7831
}
}
},
"val_teacher2": {
"all": {
"n": 447,
"accuracy": 0.8322,
"nll": 0.4435,
"ece": 0.0627,
"mean_conf": 0.8747
},
"by_type": {
"choice": {
"n": 265,
"accuracy": 0.8377,
"nll": 0.4219,
"ece": 0.0503,
"mean_conf": 0.8858
},
"noul": {
"n": 120,
"accuracy": 0.85,
"nll": 0.3702,
"ece": 0.0827,
"mean_conf": 0.9034
},
"score": {
"n": 62,
"accuracy": 0.7742,
"nll": 0.6773,
"ece": 0.1441,
"mean_conf": 0.772
}
}
},
"cal_human": {
"all": {
"n": 1595,
"accuracy": 0.8564,
"nll": 0.3892,
"ece": 0.0205,
"mean_conf": 0.8717
},
"by_type": {
"choice": {
"n": 1595,
"accuracy": 0.8564,
"nll": 0.3892,
"ece": 0.0205,
"mean_conf": 0.8717
},
"noul": null,
"score": null
}
},
"val_replay4": {
"all": {
"n": 1000,
"accuracy": 0.889,
"nll": 0.2848,
"ece": 0.0297,
"mean_conf": 0.8702
},
"by_type": {
"choice": {
"n": 1000,
"accuracy": 0.889,
"nll": 0.2848,
"ece": 0.0297,
"mean_conf": 0.8702
},
"noul": null,
"score": null
}
}
},
"global_T": {
"heldout_jb": {
"all": {
"n": 5000,
"accuracy": 0.5562,
"nll": 1.2937,
"ece": 0.163,
"mean_conf": 0.7192
},
"by_type": {
"choice": {
"n": 3293,
"accuracy": 0.5056,
"nll": 1.5059,
"ece": 0.1724,
"mean_conf": 0.678
},
"noul": {
"n": 1289,
"accuracy": 0.7114,
"nll": 0.7112,
"ece": 0.1463,
"mean_conf": 0.8577
},
"score": {
"n": 418,
"accuracy": 0.4761,
"nll": 1.4183,
"ece": 0.1402,
"mean_conf": 0.6163
}
}
},
"test_teacher2": {
"all": {
"n": 449,
"accuracy": 0.8196,
"nll": 0.4381,
"ece": 0.0497,
"mean_conf": 0.8664
},
"by_type": {
"choice": {
"n": 257,
"accuracy": 0.8016,
"nll": 0.5058,
"ece": 0.058,
"mean_conf": 0.8596
},
"noul": {
"n": 130,
"accuracy": 0.8692,
"nll": 0.2755,
"ece": 0.0602,
"mean_conf": 0.9294
},
"score": {
"n": 62,
"accuracy": 0.7903,
"nll": 0.4984,
"ece": 0.0798,
"mean_conf": 0.7623
}
}
},
"guard": {
"all": {
"n": 2994,
"accuracy": 0.8186,
"nll": 0.4871,
"ece": 0.0194,
"mean_conf": 0.836
},
"by_type": {
"choice": {
"n": 2994,
"accuracy": 0.8186,
"nll": 0.4871,
"ece": 0.0194,
"mean_conf": 0.836
},
"noul": null,
"score": null
}
},
"val_jb": {
"all": {
"n": 5000,
"accuracy": 0.796,
"nll": 0.5269,
"ece": 0.0264,
"mean_conf": 0.8224
},
"by_type": {
"choice": {
"n": 3374,
"accuracy": 0.7647,
"nll": 0.6267,
"ece": 0.0303,
"mean_conf": 0.795
},
"noul": {
"n": 1273,
"accuracy": 0.901,
"nll": 0.223,
"ece": 0.0172,
"mean_conf": 0.9146
},
"score": {
"n": 353,
"accuracy": 0.7167,
"nll": 0.6687,
"ece": 0.0363,
"mean_conf": 0.7514
}
}
},
"val_teacher": {
"all": {
"n": 944,
"accuracy": 0.8379,
"nll": 0.433,
"ece": 0.046,
"mean_conf": 0.8722
},
"by_type": {
"choice": {
"n": 540,
"accuracy": 0.8315,
"nll": 0.4654,
"ece": 0.0435,
"mean_conf": 0.8558
},
"noul": {
"n": 284,
"accuracy": 0.8873,
"nll": 0.3405,
"ece": 0.0634,
"mean_conf": 0.9331
},
"score": {
"n": 120,
"accuracy": 0.75,
"nll": 0.5064,
"ece": 0.0603,
"mean_conf": 0.8016
}
}
},
"val_teacher2": {
"all": {
"n": 447,
"accuracy": 0.8277,
"nll": 0.4695,
"ece": 0.0806,
"mean_conf": 0.8852
},
"by_type": {
"choice": {
"n": 265,
"accuracy": 0.8377,
"nll": 0.4233,
"ece": 0.0546,
"mean_conf": 0.8868
},
"noul": {
"n": 120,
"accuracy": 0.85,
"nll": 0.4441,
"ece": 0.1059,
"mean_conf": 0.9311
},
"score": {
"n": 62,
"accuracy": 0.7419,
"nll": 0.7165,
"ece": 0.1556,
"mean_conf": 0.7893
}
}
},
"cal_human": {
"all": {
"n": 1595,
"accuracy": 0.8564,
"nll": 0.3893,
"ece": 0.0195,
"mean_conf": 0.8733
},
"by_type": {
"choice": {
"n": 1595,
"accuracy": 0.8564,
"nll": 0.3893,
"ece": 0.0195,
"mean_conf": 0.8733
},
"noul": null,
"score": null
}
},
"val_replay4": {
"all": {
"n": 1000,
"accuracy": 0.889,
"nll": 0.2843,
"ece": 0.0287,
"mean_conf": 0.8713
},
"by_type": {
"choice": {
"n": 1000,
"accuracy": 0.889,
"nll": 0.2843,
"ece": 0.0287,
"mean_conf": 0.8713
},
"noul": null,
"score": null
}
}
}
},
"fixtures": {
"general_validation": {
"this": {
"rows": 847,
"accuracy": 0.8500590318772137,
"macro_accuracy": 0.8552272255409907,
"groups": 65,
"nll": 0.43237405419192004,
"ece": 0.03505942904541031,
"brier": 0.22353081852050935,
"mean_confidence": 0.8244136475475226
},
"paired": {
"cand4b_B4_e2_tt-cand4b_B4_e2": {
"accuracy": {
"delta": 0.0,
"ci95": [
0.0,
0.0
]
},
"nll": {
"delta": 0.00012970495542040443,
"ci95": [
-0.00039863639304211823,
0.0005942988193083918
]
}
},
"cand4b_B4_e2_tt-v1_4b_p130": {
"accuracy": {
"delta": -0.010625737898465172,
"ci95": [
-0.021251475796930343,
0.0
]
},
"nll": {
"delta": 0.015307099810435664,
"ci95": [
0.0030912070436396634,
0.028028207832146323
]
}
},
"cand4b_B4_e2_tt-v2_4b_p130": {
"accuracy": {
"delta": 0.0,
"ci95": [
-0.015348288075560802,
0.015348288075560802
]
},
"nll": {
"delta": 0.013765296214476044,
"ci95": [
-0.006225581100979938,
0.0345539752628619
]
}
}
}
},
"typesafe": {
"this": {
"rows": 102,
"accuracy": 0.8431372549019608,
"macro_accuracy": 0.8464696223316912,
"groups": 4,
"nll": 0.44128428424617644,
"ece": 0.06267209380280735,
"brier": 0.24132394423929263,
"mean_confidence": 0.8996653276331285,
"mean_total_variation_to_reference": 0.19246147475275616
},
"paired": {
"cand4b_B4_e2_tt-cand4b_B4_e2": {
"accuracy": {
"delta": 0.0,
"ci95": [
0.0,
0.0
]
},
"nll": {
"delta": -0.0017070072924830098,
"ci95": [
-0.003544773928864442,
-8.629601238631066e-05
]
}
},
"cand4b_B4_e2_tt-v1_4b_p130": {
"accuracy": {
"delta": 0.029411764705882353,
"ci95": [
-0.029411764705882353,
0.08823529411764706
]
},
"nll": {
"delta": -0.16956755666314244,
"ci95": [
-0.3236270765220259,
-0.035752501984007506
]
}
},
"cand4b_B4_e2_tt-v2_4b_p130": {
"accuracy": {
"delta": -0.0196078431372549,
"ci95": [
-0.0784313725490196,
0.0392156862745098
]
},
"nll": {
"delta": 0.03116252024698791,
"ci95": [
-0.06909971743191749,
0.13434316002254298
]
}
}
}
},
"openjev_external": {
"this": {
"rows": 5252,
"accuracy": 0.6597486671744097,
"macro_accuracy": 0.8063444444444444,
"groups": 3,
"nll": 0.8457289344223444,
"ece": 0.1539857582574297,
"brier": 0.5022800176356607,
"mean_confidence": 0.8111537299704116
},
"paired": {
"cand4b_B4_e2_tt-cand4b_B4_e2": {
"accuracy": {
"delta": 0.0,
"ci95": [
0.0,
0.0
]
},
"nll": {
"delta": -0.003617502816960803,
"ci95": [
-0.003919285763621306,
-0.00332506503930084
]
}
},
"cand4b_B4_e2_tt-v1_4b_p130": {
"accuracy": {
"delta": 0.020944402132520943,
"ci95": [
0.012376237623762377,
0.029322162985529324
]
},
"nll": {
"delta": -0.047333755296254304,
"ci95": [
-0.059559262901540976,
-0.035193633735333484
]
}
},
"cand4b_B4_e2_tt-v2_4b_p130": {
"accuracy": {
"delta": -0.007425742574257425,
"ci95": [
-0.015993907083015995,
0.0017136329017517135
]
},
"nll": {
"delta": 0.05671352997929895,
"ci95": [
0.04359541016972144,
0.07033520922345497
]
}
}
}
},
"mind2web": {
"this": {
"rows": 1770,
"accuracy": 0.8751412429378531,
"macro_accuracy": 0.8773196126201471,
"groups": 3,
"nll": 0.37523612083453944,
"ece": 0.016833950116135952,
"brier": 0.18402882486455008,
"mean_confidence": 0.8624463401776923
},
"paired": {
"cand4b_B4_e2_tt-cand4b_B4_e2": {
"accuracy": {
"delta": 0.0,
"ci95": [
0.0,
0.0
]
},
"nll": {
"delta": 0.00026909733615400604,
"ci95": [
-4.997823592689937e-05,
0.0006061414472582659
]
}
},
"cand4b_B4_e2_tt-v1_4b_p130": {
"accuracy": {
"delta": -0.00847457627118644,
"ci95": [
-0.01694915254237288,
0.0
]
},
"nll": {
"delta": 0.00924747244030173,
"ci95": [
-0.004092843962589085,
0.022512164121517977
]
}
},
"cand4b_B4_e2_tt-v2_4b_p130": {
"accuracy": {
"delta": 0.0011299435028248588,
"ci95": [
-0.00847457627118644,
0.011299435028248588
]
},
"nll": {
"delta": -0.018244809747118285,
"ci95": [
-0.032040489157299956,
-0.005027723688309381
]
}
}
}
}
},
"games": {
"cand4b_B4_e2_tt-cand4b_B4_e2|sampled|all": {
"n": 234,
"a": 0.2692307692307692,
"b": 0.2692307692307692,
"delta": 0.0,
"ci95": [
-0.004273504273504274,
0.004273504273504274
]
},
"cand4b_B4_e2_tt-cand4b_B4_e2|sampled|bag_game": {
"n": 64,
"a": 0.51953125,
"b": 0.51953125,
"delta": 0.0,
"ci95": [
-0.01171875,
0.01171875
]
},
"cand4b_B4_e2_tt-cand4b_B4_e2|sampled|stochastic_grid": {
"n": 64,
"a": 0.16796875,
"b": 0.16796875,
"delta": 0.0,
"ci95": [
-0.01171875,
0.01171875
]
},
"cand4b_B4_e2_tt-cand4b_B4_e2|sampled|tic_tac_toe": {
"n": 74,
"a": 0.2533783783783784,
"b": 0.2533783783783784,
"delta": 0.0,
"ci95": [
0.0,
0.0
]
},
"cand4b_B4_e2_tt-cand4b_B4_e2|sampled|exact_minesweeper": {
"n": 32,
"a": 0.0078125,
"b": 0.0078125,
"delta": 0.0,
"ci95": [
0.0,
0.0
]
},
"cand4b_B4_e2_tt-cand4b_B4_e2|greedy|all": {
"n": 234,
"a": 0.25213675213675213,
"b": 0.25213675213675213,
"delta": 0.0,
"ci95": [
0.0,
0.0
]
},
"cand4b_B4_e2_tt-cand4b_B4_e2|greedy|bag_game": {
"n": 64,
"a": 0.53125,
"b": 0.53125,
"delta": 0.0,
"ci95": [
0.0,
0.0
]
},
"cand4b_B4_e2_tt-cand4b_B4_e2|greedy|stochastic_grid": {
"n": 64,
"a": 0.109375,
"b": 0.109375,
"delta": 0.0,
"ci95": [
0.0,
0.0
]
},
"cand4b_B4_e2_tt-cand4b_B4_e2|greedy|tic_tac_toe": {
"n": 74,
"a": 0.24324324324324326,
"b": 0.24324324324324326,
"delta": 0.0,
"ci95": [
0.0,
0.0
]
},
"cand4b_B4_e2_tt-cand4b_B4_e2|greedy|exact_minesweeper": {
"n": 32,
"a": 0.0,
"b": 0.0,
"delta": 0.0,
"ci95": [
0.0,
0.0
]
},
"cand4b_B4_e2_tt-v1_4b_p130|sampled|all": {
"n": 234,
"a": 0.2692307692307692,
"b": 0.2777777777777778,
"delta": -0.008547008547008548,
"ci95": [
-0.02564102564102564,
0.009615384615384616
]
},
"cand4b_B4_e2_tt-v1_4b_p130|sampled|bag_game": {
"n": 64,
"a": 0.51953125,
"b": 0.56640625,
"delta": -0.046875,
"ci95": [
-0.08984375,
-0.00390625
]
},
"cand4b_B4_e2_tt-v1_4b_p130|sampled|stochastic_grid": {
"n": 64,
"a": 0.16796875,
"b": 0.1640625,
"delta": 0.00390625,
"ci95": [
-0.02734375,
0.03515625
]
},
"cand4b_B4_e2_tt-v1_4b_p130|sampled|tic_tac_toe": {
"n": 74,
"a": 0.2533783783783784,
"b": 0.24324324324324326,
"delta": 0.010135135135135136,
"ci95": [
-0.013513513513513514,
0.037162162162162164
]
},
"cand4b_B4_e2_tt-v1_4b_p130|sampled|exact_minesweeper": {
"n": 32,
"a": 0.0078125,
"b": 0.0078125,
"delta": 0.0,
"ci95": [
-0.0234375,
0.0234375
]
},
"cand4b_B4_e2_tt-v1_4b_p130|greedy|all": {
"n": 234,
"a": 0.25213675213675213,
"b": 0.2905982905982906,
"delta": -0.038461538461538464,
"ci95": [
-0.07264957264957266,
-0.004273504273504274
]
},
"cand4b_B4_e2_tt-v1_4b_p130|greedy|bag_game": {
"n": 64,
"a": 0.53125,
"b": 0.625,
"delta": -0.09375,
"ci95": [
-0.171875,
-0.03125
]
},
"cand4b_B4_e2_tt-v1_4b_p130|greedy|stochastic_grid": {
"n": 64,
"a": 0.109375,
"b": 0.125,
"delta": -0.015625,
"ci95": [
-0.07851562499999987,
0.046875
]
},
"cand4b_B4_e2_tt-v1_4b_p130|greedy|tic_tac_toe": {
"n": 74,
"a": 0.24324324324324326,
"b": 0.2702702702702703,
"delta": -0.02702702702702703,
"ci95": [
-0.0945945945945946,
0.04054054054054054
]
},
"cand4b_B4_e2_tt-v1_4b_p130|greedy|exact_minesweeper": {
"n": 32,
"a": 0.0,
"b": 0.0,
"delta": 0.0,
"ci95": [
0.0,
0.0
]
},
"cand4b_B4_e2_tt-v2_4b_p130|sampled|all": {
"n": 234,
"a": 0.2692307692307692,
"b": 0.22435897435897437,
"delta": 0.04487179487179487,
"ci95": [
0.024572649572649572,
0.06623931623931624
]
},
"cand4b_B4_e2_tt-v2_4b_p130|sampled|bag_game": {
"n": 64,
"a": 0.51953125,
"b": 0.37890625,
"delta": 0.140625,
"ci95": [
0.08203125,
0.19921875
]
},
"cand4b_B4_e2_tt-v2_4b_p130|sampled|stochastic_grid": {
"n": 64,
"a": 0.16796875,
"b": 0.16015625,
"delta": 0.0078125,
"ci95": [
-0.0234375,
0.0390625
]
},
"cand4b_B4_e2_tt-v2_4b_p130|sampled|tic_tac_toe": {
"n": 74,
"a": 0.2533783783783784,
"b": 0.24324324324324326,
"delta": 0.010135135135135136,
"ci95": [
-0.010135135135135136,
0.033783783783783786
]
},
"cand4b_B4_e2_tt-v2_4b_p130|sampled|exact_minesweeper": {
"n": 32,
"a": 0.0078125,
"b": 0.0,
"delta": 0.0078125,
"ci95": [
0.0,
0.0234375
]
},
"cand4b_B4_e2_tt-v2_4b_p130|greedy|all": {
"n": 234,
"a": 0.25213675213675213,
"b": 0.2777777777777778,
"delta": -0.02564102564102564,
"ci95": [
-0.0641025641025641,
0.01282051282051282
]
},
"cand4b_B4_e2_tt-v2_4b_p130|greedy|bag_game": {
"n": 64,
"a": 0.53125,
"b": 0.484375,
"delta": 0.046875,
"ci95": [
-0.03125,
0.125
]
},
"cand4b_B4_e2_tt-v2_4b_p130|greedy|stochastic_grid": {
"n": 64,
"a": 0.109375,
"b": 0.1875,
"delta": -0.078125,
"ci95": [
-0.15625,
0.0
]
},
"cand4b_B4_e2_tt-v2_4b_p130|greedy|tic_tac_toe": {
"n": 74,
"a": 0.24324324324324326,
"b": 0.2972972972972973,
"delta": -0.05405405405405406,
"ci95": [
-0.12162162162162163,
0.02702702702702703
]
},
"cand4b_B4_e2_tt-v2_4b_p130|greedy|exact_minesweeper": {
"n": 32,
"a": 0.0,
"b": 0.0,
"delta": 0.0,
"ci95": [
0.0,
0.0
]
}
},
"browser": {
"cand4b_B4_e2_tt-cand4b_B4_e2|sampled|all": {
"n": 176,
"a": 0.9318181818181818,
"b": 0.9318181818181818,
"delta": 0.0,
"ci95": [
0.0,
0.0
]
},
"cand4b_B4_e2_tt-cand4b_B4_e2|sampled|rewarded": {
"n": 128,
"a": 0.953125,
"b": 0.953125,
"delta": 0.0,
"ci95": [
0.0,
0.0
]
},
"cand4b_B4_e2_tt-cand4b_B4_e2|sampled|held_out": {
"n": 48,
"a": 0.875,
"b": 0.875,
"delta": 0.0,
"ci95": [
0.0,
0.0
]
},
"cand4b_B4_e2_tt-cand4b_B4_e2|greedy|all": {
"n": 176,
"a": 0.9375,
"b": 0.9375,
"delta": 0.0,
"ci95": [
0.0,
0.0
]
},
"cand4b_B4_e2_tt-cand4b_B4_e2|greedy|rewarded": {
"n": 128,
"a": 0.9609375,
"b": 0.9609375,
"delta": 0.0,
"ci95": [
0.0,
0.0
]
},
"cand4b_B4_e2_tt-cand4b_B4_e2|greedy|held_out": {
"n": 48,
"a": 0.875,
"b": 0.875,
"delta": 0.0,
"ci95": [
0.0,
0.0
]
},
"cand4b_B4_e2_tt-v1_4b_p130|sampled|all": {
"n": 176,
"a": 0.9318181818181818,
"b": 0.9090909090909091,
"delta": 0.022727272727272728,
"ci95": [
-0.017045454545454544,
0.0625
]
},
"cand4b_B4_e2_tt-v1_4b_p130|sampled|rewarded": {
"n": 128,
"a": 0.953125,
"b": 0.9609375,
"delta": -0.0078125,
"ci95": [
-0.0390625,
0.0234375
]
},
"cand4b_B4_e2_tt-v1_4b_p130|sampled|held_out": {
"n": 48,
"a": 0.875,
"b": 0.7708333333333334,
"delta": 0.10416666666666667,
"ci95": [
0.0,
0.20833333333333334
]
},
"cand4b_B4_e2_tt-v1_4b_p130|greedy|all": {
"n": 176,
"a": 0.9375,
"b": 0.9147727272727273,
"delta": 0.022727272727272728,
"ci95": [
-0.005681818181818182,
0.056818181818181816
]
},
"cand4b_B4_e2_tt-v1_4b_p130|greedy|rewarded": {
"n": 128,
"a": 0.9609375,
"b": 0.9765625,
"delta": -0.015625,
"ci95": [
-0.0390625,
0.0
]
},
"cand4b_B4_e2_tt-v1_4b_p130|greedy|held_out": {
"n": 48,
"a": 0.875,
"b": 0.75,
"delta": 0.125,
"ci95": [
0.041666666666666664,
0.22916666666666666
]
},
"cand4b_B4_e2_tt-v2_4b_p130|sampled|all": {
"n": 176,
"a": 0.9318181818181818,
"b": 0.8806818181818182,
"delta": 0.05113636363636364,
"ci95": [
0.005681818181818182,
0.09659090909090909
]
},
"cand4b_B4_e2_tt-v2_4b_p130|sampled|rewarded": {
"n": 128,
"a": 0.953125,
"b": 0.9296875,
"delta": 0.0234375,
"ci95": [
-0.0234375,
0.0703125
]
},
"cand4b_B4_e2_tt-v2_4b_p130|sampled|held_out": {
"n": 48,
"a": 0.875,
"b": 0.75,
"delta": 0.125,
"ci95": [
0.0,
0.25
]
},
"cand4b_B4_e2_tt-v2_4b_p130|greedy|all": {
"n": 176,
"a": 0.9375,
"b": 0.9261363636363636,
"delta": 0.011363636363636364,
"ci95": [
-0.017045454545454544,
0.045454545454545456
]
},
"cand4b_B4_e2_tt-v2_4b_p130|greedy|rewarded": {
"n": 128,
"a": 0.9609375,
"b": 0.96875,
"delta": -0.0078125,
"ci95": [
-0.0234375,
0.0
]
},
"cand4b_B4_e2_tt-v2_4b_p130|greedy|held_out": {
"n": 48,
"a": 0.875,
"b": 0.8125,
"delta": 0.0625,
"ci95": [
-0.041666666666666664,
0.16666666666666666
]
}
},
"text_games_greedy": {
"pong": -5.0,
"freeway": 0.0,
"breakout": 35.0,
"frozenlake": 0.0,
"cliffwalking": -13.0,
"blackjack": -0.6,
"minigrid_empty": 0.0,
"minigrid_lavagap": 0.0,
"minigrid_doorkey": 0.0,
"babyai_goto": 0.1915625
},
"probes": {
"router_n": 31,
"router_tier": 0.968,
"needs_live_data": 0.839,
"commands_n": 45,
"command_risk": 0.889,
"destructive_called_safe": 0,
"outside_project": 0.933,
"browser_element": 0.938,
"browser_action": 0.75,
"batteries": {
"generic": 1.0,
"specific": 1.0,
"catchall": 0.95,
"noul_acc": 1.0,
"noul_brier": 0.01,
"n_choice": 60,
"n_noul": 49,
"abstain_battery": "8/8"
}
},
"issue9": {
"c_1": {
"pred": 26,
"gold": 6,
"ok": false,
"p_gold": 0.198,
"p_pred": 0.764,
"T": 1.099
},
"c_2": {
"pred": 20,
"gold": 20,
"ok": true,
"p_gold": 0.409,
"p_pred": 0.409,
"T": 1.099
},
"b_10": {
"pred": 0,
"gold": 0,
"ok": true,
"p_gold": 0.732,
"p_pred": 0.732,
"T": 1.099
},
"a2_4": {
"pred": 4,
"gold": 4,
"ok": true,
"p_gold": 0.577,
"p_pred": 0.577,
"T": 1.099
}
},
"bespoke": {
"vitaminc-dev": {
"n": 599,
"type": "choice",
"acc": 0.7429,
"ece": 0.1456,
"brier": 0.3945,
"nll": 0.7789,
"trained": false,
"sec": 11.8
},
"massive-en-US": {
"n": 350,
"type": "choice",
"acc": 0.8629,
"ece": 0.0411,
"brier": 0.1936,
"nll": 0.4173,
"trained": true,
"sec": 6.2
},
"massive-de-DE": {
"n": 350,
"type": "choice",
"acc": 0.84,
"ece": 0.0297,
"brier": 0.2269,
"nll": 0.4947,
"trained": false,
"sec": 4.5
},
"boolq": {
"n": 300,
"type": "noul",
"acc": 0.8667,
"ece": 0.0319,
"brier": 0.1862,
"nll": 0.3007,
"trained": true,
"sec": 6.2
},
"squad2": {
"n": 299,
"type": "noul",
"acc": 0.7893,
"ece": 0.0441,
"brier": 0.2955,
"nll": 0.452,
"trained": false,
"sec": 7.2
},
"paws": {
"n": 250,
"type": "noul",
"acc": 0.764,
"ece": 0.1238,
"brier": 0.3398,
"nll": 0.5538,
"trained": true,
"sec": 3.0
},
"multinli": {
"n": 299,
"type": "choice",
"acc": 0.9331,
"ece": 0.0103,
"brier": 0.1089,
"nll": 0.2099,
"trained": true,
"sec": 3.1
},
"civil_comments": {
"n": 300,
"type": "noul",
"acc": 0.8733,
"ece": 0.0566,
"brier": 0.1917,
"nll": 0.3199,
"trained": true,
"sec": 3.2
},
"aegis2": {
"n": 250,
"type": "noul",
"acc": 0.804,
"ece": 0.0467,
"brier": 0.2797,
"nll": 0.4527,
"trained": false,
"sec": 6.1
},
"helpsteer2": {
"n": 249,
"type": "score",
"acc": 0.4498,
"ece": 0.142,
"brier": 0.6713,
"nll": 1.2502,
"trained": true,
"sec": 25.8,
"score_mae": 0.797
},
"summeval-relevance": {
"n": 240,
"type": "score",
"acc": 0.3958,
"ece": 0.0696,
"brier": 0.6844,
"nll": 1.2541,
"trained": false,
"sec": 20.1,
"score_mae": 0.6172
},
"summeval-consistency": {
"n": 144,
"type": "score",
"acc": 0.7986,
"ece": 0.3095,
"brier": 0.4741,
"nll": 0.9007,
"trained": false,
"sec": 12.2,
"score_mae": 0.7974
},
"pubmedqa": {
"n": 250,
"type": "choice",
"acc": 0.708,
"ece": 0.0863,
"brier": 0.4012,
"nll": 0.7205,
"trained": true,
"sec": 3.8
},
"_macro": 0.756,
"_micro": 0.7652,
"_macro_untrained": 0.7284
},
"jevbench_public": {
"easy": {
"n": 48,
"accuracy": 1.0,
"invalid": 0,
"ece": 0.0027979166666670663,
"by_family": {
"extraction": {
"n": 12,
"accuracy": 1.0
},
"fact": {
"n": 12,
"accuracy": 1.0
},
"intent": {
"n": 12,
"accuracy": 1.0
},
"tool_selection": {
"n": 12,
"accuracy": 1.0
}
}
},
"standard": {
"n": 72,
"accuracy": 0.9861111111111112,
"invalid": 0,
"ece": 0.0753152777777778,
"by_family": {
"adequacy": {
"n": 12,
"accuracy": 0.9166666666666666
},
"extraction": {
"n": 12,
"accuracy": 1.0
},
"intent": {
"n": 12,
"accuracy": 1.0
},
"ordinal": {
"n": 12,
"accuracy": 1.0
},
"policy": {
"n": 12,
"accuracy": 1.0
},
"routing": {
"n": 12,
"accuracy": 1.0
}
}
},
"hard": {
"n": 111,
"accuracy": 0.6486486486486487,
"invalid": 0,
"ece": 0.18370720720720732,
"by_family": {
"adversarial": {
"n": 6,
"accuracy": 1.0
},
"ambiguous": {
"n": 7,
"accuracy": 0.7142857142857143
},
"judge_hard": {
"n": 17,
"accuracy": 0.5294117647058824
},
"long_policy": {
"n": 19,
"accuracy": 0.47368421052631576
},
"multi_hop": {
"n": 18,
"accuracy": 0.8333333333333334
},
"probability": {
"n": 10,
"accuracy": 0.8
},
"routing_hard": {
"n": 5,
"accuracy": 1.0
},
"temporal_numeric": {
"n": 15,
"accuracy": 0.3333333333333333
},
"tradeoff": {
"n": 6,
"accuracy": 0.3333333333333333
},
"trap": {
"n": 8,
"accuracy": 1.0
}
}
}
},
"references": {
"v1_4b": {
"reg_in": 0.8338,
"reg_out": 0.7876,
"reg_in_nll": 0.4044,
"reg_out_nll": 0.5583,
"reg_in_ece": 0.0269,
"reg_out_ece": 0.0708
},
"v2_4b": {
"reg_in": 0.8241,
"reg_out": 0.7788,
"reg_in_nll": 0.4411,
"reg_out_nll": 0.5663,
"reg_in_ece": 0.0413,
"reg_out_ece": 0.0803
}
},
"speed": "not measured again: the architecture and size equal the parent's, and the temperature map does not change the computation"
}